© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 471
    Prev
    Next
    INDEX
    Explanations

    information about safety features and facilities in a hotel or accommodation setting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.10
    0.4%
    1557
    +0.07
    0.3%
    1896
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1048
    +0.10
    0.04
    948
    +0.07
    0.04
    207
    +0.06
    0.04
    Negative Logits
    <bos>
    -1.46
     realize
    -0.65
    }{||
    -0.64
    int
    -0.59
     participated
    -0.59
    displayquote
    -0.58
    public
    -0.58
    /*
    -0.58
     participate
    -0.58
    ComponentModel
    -0.58
    POSITIVE LOGITS
     safe
    2.06
     Safe
    1.93
    safe
    1.87
     SAFE
    1.81
    Safe
    1.77
    SAFE
    1.54
     safest
    1.50
     napoli
    1.48
     wien
    1.47
     safer
    1.47
    Activations Density 0.096%

    No Known Activations