© 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. 513
    Prev
    Next
    INDEX
    Explanations

    phrases related to software companies and gaming terminology

    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
    690
    +0.16
    0.5%
    1871
    +0.12
    0.4%
    924
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.16
    0.12
    2044
    +0.12
    0.09
    823
    +0.08
    0.07
    Negative Logits
    Về
    -1.23
    Sản
    -1.11
     immer
    -1.10
     den
    -1.10
    а
    -1.10
    Bộ
    -1.10
     die
    -1.09
    Thành
    -1.09
     far
    -1.09
    Chỉ
    -1.09
    POSITIVE LOGITS
     increa
    3.75
     Mlle
    3.64
     affor
    3.64
     scrat
    3.61
     guarante
    3.55
     perfet
    3.55
     vété
    3.53
     accla
    3.50
     snoopy
    3.49
     madonna
    3.49
    Activations Density 0.674%

    No Known Activations