© 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. 6587
    Prev
    Next
    INDEX
    Explanations

    references to academic publications or content on topics related to research and academia

    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
    200
    +0.19
    1.0%
    1035
    +0.16
    0.8%
    410
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.19
    0.04
    200
    +0.16
    0.04
    1741
    +0.14
    -0.01
    Negative Logits
    <bos>
    -1.02
    /**
    -0.82
    āci
    -0.70
     Derivation
    -0.65
    īg
    -0.62
     Stretcher
    -0.61
     Suction
    -0.60
    <?
    -0.59
     Ignorance
    -0.58
     Correlations
    -0.58
    POSITIVE LOGITS
     mezza
    0.85
     Ottobre
    0.81
     hecta
    0.80
     Luglio
    0.79
     paradiso
    0.78
     gamba
    0.76
     divertimento
    0.76
     vesta
    0.74
     dises
    0.74
     CiNii
    0.74
    Activations Density 0.546%

    No Known Activations