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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 8888
    Prev
    Next
    INDEX
    Explanations

    the names of individuals or entities who developed or oversaw a project or authored a document

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.30
    1.3%
    1103
    +0.10
    0.4%
    752
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.30
    0.07
    506
    +0.10
    0.06
    1103
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.51
    ⓧ
    -0.79
    /***
    
    -0.70
    public
    -0.64
    /**
    -0.62
     continue
    -0.60
    add
    -0.59
     also
    -0.58
            
    -0.58
    加
    -0.58
    POSITIVE LOGITS
     accla
    1.39
     Khart
    1.36
     Keny
    1.34
     Juf
    1.31
     véhic
    1.30
     Minang
    1.29
     affor
    1.27
     soulign
    1.23
     Momb
    1.21
     délib
    1.21
    Activations Density 0.721%

    No Known Activations