© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4235
    Prev
    Next
    INDEX
    Explanations

    a specific string pattern ("F" followed by a number) or the word "suff" followed by "f" along with other strings related to software development and technical terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    281
    +0.16
    0.6%
    1145
    +0.15
    0.5%
    297
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1145
    +0.16
    0.04
    281
    +0.15
    0.04
    297
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.03
    Ekster
    -0.79
    prägt
    -0.70
    Ilustra
    -0.68
    Litteratur
    -0.68
    Fontes
    -0.68
    película
    -0.67
    Iné
    -0.67
    Семья
    -0.66
    Referencoj
    -0.66
    POSITIVE LOGITS
     bandung
    1.27
     dises
    1.26
     lele
    1.23
     kef
    1.23
     jawa
    1.21
     hina
    1.21
     pama
    1.20
     jaya
    1.19
     abnorm
    1.18
     cyr
    1.18
    Activations Density 0.090%

    No Known Activations