© 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. 315
    Prev
    Next
    INDEX
    Explanations

    technical data related to data transfers and file information

    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
    +0.27
    1.4%
    453
    +0.18
    0.9%
    1343
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.27
    0.15
    1419
    +0.18
    0.10
    453
    +0.17
    0.12
    Negative Logits
    <bos>
    -1.83
    ,
    -0.94
     to
    -0.90
     in
    -0.88
     do
    -0.88
     for
    -0.87
     at
    -0.87
    、
    -0.87
    的
    -0.86
     on
    -0.85
    POSITIVE LOGITS
     stockholm
    2.44
     wien
    2.37
     affor
    2.31
     ?...
    2.29
     accla
    2.27
     „,
    2.25
     dispen
    2.24
     emphat
    2.24
     effe
    2.22
     oner
    2.20
    Activations Density 1.675%

    No Known Activations