© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 603
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development, programming languages, and internet technologies

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    678
    +0.09
    0.3%
    1978
    +0.08
    0.3%
    876
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.09
    0.07
    16
    +0.08
    0.06
    344
    +0.08
    0.05
    Negative Logits
    <?
    -0.75
     through
    -0.71
     continue
    -0.70
    会话
    -0.70
    管理器
    -0.70
     nor
    -0.69
     together
    -0.69
     au
    -0.69
    比如说
    -0.69
    <bos>
    -0.69
    POSITIVE LOGITS
     affor
    2.33
     wien
    2.27
     lidl
    2.27
     stockholm
    2.25
     squa
    2.25
     effe
    2.24
     milano
    2.23
     increa
    2.19
     napoli
    2.18
     nece
    2.16
    Activations Density 0.298%

    No Known Activations