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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13845
    Prev
    Next
    INDEX
    Explanations

    URLs for images

    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
    1978
    +0.10
    0.3%
    1820
    +0.10
    0.3%
    86
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.04
    1803
    +0.10
    0.03
    267
    +0.09
    0.04
    Negative Logits
     hairc
    -1.23
     snoopy
    -1.22
     outlander
    -1.15
     milf
    -1.12
     indescri
    -1.08
     shenan
    -1.08
     madonna
    -1.04
     yoda
    -1.04
     scrat
    -1.04
     cushi
    -1.03
    POSITIVE LOGITS
     lemp
    0.71
    2
    0.63
     perak
    0.63
     krim
    0.61
     seksi
    0.60
     silikon
    0.59
     ekos
    0.59
     karbon
    0.58
    iquest
    0.58
     panik
    0.56
    Activations Density 0.144%

    No Known Activations