© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 221
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need for action or separate items within a list

    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
    +0.18
    0.9%
    976
    +0.11
    0.5%
    860
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    860
    +0.18
    0.03
    976
    +0.11
    0.03
    347
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.98
    ⓧ
    -0.82
    <?
    -0.78
    /**
    -0.72
    <?
    -0.71
    /*!
    -0.68
    /***
    -0.67
    //{
    -0.64
    Enllaços
    -0.59
    HasIndex
    -0.59
    POSITIVE LOGITS
     stockholm
    1.58
     frankfurt
    1.44
     Juf
    1.43
     wien
    1.42
     thut
    1.41
     fep
    1.35
     aen
    1.32
     fta
    1.31
     eiffel
    1.31
     Confu
    1.31
    Activations Density 0.151%

    No Known Activations