© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 872
    Prev
    Next
    INDEX
    Explanations

    definitions or explanations of 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
    1575
    +0.13
    0.4%
    1839
    +0.11
    0.4%
    687
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1575
    +0.13
    0.05
    683
    +0.11
    0.04
    2033
    +0.10
    0.04
    Negative Logits
     ibiza
    -0.78
     Realt
    -0.73
     antem
    -0.69
     oreo
    -0.69
     gliss
    -0.68
     flam
    -0.68
     pleins
    -0.67
     parma
    -0.65
     coq
    -0.64
     Ancho
    -0.64
    POSITIVE LOGITS
     usually
    0.90
    Usually
    0.82
     Usually
    0.80
     typically
    0.79
    usually
    0.74
     normally
    0.74
    бычно
    0.71
    Typically
    0.67
     Typically
    0.66
    typically
    0.62
    Activations Density 0.140%

    No Known Activations