Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 167
    Prev
    Next
    INDEX
    Explanations

    texts discussing limitations or constraints

    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
    50
    +0.10
    0.4%
    1103
    +0.07
    0.3%
    1622
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.10
    0.04
    1636
    +0.07
    0.04
    1622
    +0.06
    0.04
    Negative Logits
    <bos>
    -1.46
    ValueGenerated
    -0.63
     do
    -0.63
    public
    -0.63
    ള്ള
    -0.62
    afterEach
    -0.62
    hline
    -0.61
    //---
    -0.61
    itemize
    -0.61
    		
    -0.61
    POSITIVE LOGITS
     limited
    1.86
     maneu
    1.80
    Limited
    1.79
     affor
    1.77
     strick
    1.75
     stockholm
    1.74
    limited
    1.69
     Limited
    1.68
     accla
    1.65
     increa
    1.63
    Activations Density 0.124%

    No Known Activations