© 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. 2061
    Prev
    Next
    INDEX
    Explanations

    information related to legal or official documentation

    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
    1150
    +0.10
    0.3%
    1799
    +0.08
    0.2%
    1997
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1997
    +0.10
    0.05
    1444
    +0.08
    0.04
    1799
    +0.07
    0.03
    Negative Logits
     emble
    -1.25
     solidar
    -1.24
     anse
    -1.23
     immen
    -1.17
     dissi
    -1.13
     peculi
    -1.13
     reger
    -1.13
     igno
    -1.13
     alkoh
    -1.12
     lein
    -1.11
    POSITIVE LOGITS
    <bos>
    0.86
     there
    0.80
    ,
    0.77
    :
    0.70
     they
    0.58
    '
    0.58
     it
    0.57
    there
    0.57
     There
    0.57
    ’
    0.56
    Activations Density 0.233%

    No Known Activations