© 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. 7611
    Prev
    Next
    INDEX
    Explanations

    code snippets containing specific patterns or characters

    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
    1343
    +0.20
    0.7%
    1705
    +0.13
    0.4%
    1896
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.20
    0.04
    981
    +0.13
    0.04
    924
    +0.13
    0.03
    Negative Logits
     Punj
    -0.87
    inderella
    -0.69
     retVal
    -0.68
    mamp
    -0.67
    fto
    -0.67
    yit
    -0.65
     rtn
    -0.64
    lijah
    -0.64
    lizabeth
    -0.63
     gend
    -0.63
    POSITIVE LOGITS
    MfG
    0.67
    /**
    0.61
    <?
    0.60
    Grüße
    0.59
     PHILOS
    0.58
    OOTDTY
    0.56
     demselben
    0.56
     GONZ
    0.56
    glLoad
    0.56
    elegante
    0.56
    Activations Density 0.069%

    No Known Activations