© 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. 3567
    Prev
    Next
    INDEX
    Explanations

    mentions of controversial topics related to medical research and privacy concerns

    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
    1842
    +0.37
    1.3%
    1577
    +0.15
    0.5%
    1978
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.37
    0.14
    198
    +0.15
    0.09
    706
    +0.14
    0.09
    Negative Logits
     snoopy
    -1.29
     lidl
    -1.27
     shenan
    -1.25
     lola
    -1.24
     increa
    -1.22
     milf
    -1.21
     accla
    -1.21
     inev
    -1.21
     alre
    -1.20
     disgra
    -1.20
    POSITIVE LOGITS
     stanovnika
    0.45
     mouseClicked
    0.45
    LAUGHTER
    0.45
    ା
    0.44
    .
    0.44
    IntoConstraints
    0.43
    EDEFAULT
    0.43
     ensalada
    0.42
    parsedMessage
    0.41
    enumi
    0.41
    Activations Density 2.142%

    No Known Activations