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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 311
    Prev
    Next
    INDEX
    Explanations

    movie titles and related 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.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
    1419
    +0.07
    0.2%
    1699
    +0.07
    0.2%
    940
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    753
    +0.07
    0.13
    2044
    +0.07
    0.11
    906
    +0.07
    0.07
    Negative Logits
     intersper
    -1.49
     apprehen
    -1.24
     quitted
    -1.23
     endow
    -1.16
     vainly
    -1.14
     gratify
    -1.13
     endeavored
    -1.12
     unve
    -1.12
     shenan
    -1.11
     endeavoured
    -1.10
    POSITIVE LOGITS
     démarrage
    1.44
     Kategor
    1.41
     remplissage
    1.39
     puits
    1.33
     levier
    1.33
     déplo
    1.31
     éclairage
    1.29
     Pièces
    1.29
     excès
    1.29
     Şi
    1.28
    Activations Density 1.074%

    No Known Activations