© 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. 250
    Prev
    Next
    INDEX
    Explanations

    terms related to guidance, instructions, and introductions

    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
    +0.21
    0.8%
    1013
    +0.09
    0.3%
    1978
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1017
    +0.21
    0.05
    1744
    +0.09
    0.05
    1695
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.28
    ⓧ
    -0.71
    ღ
    -0.65
    HasColumnType
    -0.63
    protected
    -0.62
    </table>
    -0.61
    parcel
    -0.61
    public
    -0.61
    ਾਲ
    -0.60
     serve
    -0.60
    POSITIVE LOGITS
     unlaw
    1.71
     squa
    1.67
     increa
    1.66
     maneu
    1.64
     secon
    1.63
     impra
    1.63
     affor
    1.62
     reluct
    1.62
     Minang
    1.60
     guarante
    1.60
    Activations Density 0.800%

    No Known Activations