Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2553
    Prev
    Next
    INDEX
    Explanations

    structured information related to statistics or quantitative data

    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
    381
    +0.13
    0.4%
    1967
    +0.11
    0.3%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1202
    +0.13
    0.04
    918
    +0.11
    0.05
    1804
    +0.11
    0.05
    Negative Logits
     for
    -0.90
     a
    -0.88
     in
    -0.85
    ,
    -0.83
     the
    -0.83
     that
    -0.82
     and
    -0.82
     as
    -0.82
     with
    -0.80
     on
    -0.80
    POSITIVE LOGITS
     alkoh
    2.40
     silikon
    2.20
     karton
    2.16
     solidar
    2.16
     kosme
    2.13
     kön
    2.11
     utop
    2.10
     keramik
    2.08
     akut
    2.02
     incess
    2.02
    Activations Density 0.257%

    No Known Activations