© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13861
    Prev
    Next
    INDEX
    Explanations

    information and instructions related to data storage and redundancy across different cloud platforms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1403
    +0.16
    0.5%
    690
    +0.14
    0.4%
    876
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.16
    0.04
    1403
    +0.14
    0.02
    1284
    +0.13
    0.03
    Negative Logits
    Trayectoria
    -0.72
    Mesmo
    -0.66
    Biografía
    -0.64
    Dijo
    -0.64
    Muerte
    -0.62
    Ainda
    -0.61
    OBJETIVO
    -0.60
    Causas
    -0.60
    Índice
    -0.60
     Mejía
    -0.59
    POSITIVE LOGITS
     frankfurt
    1.28
     vespa
    1.22
     scrat
    1.22
     affor
    1.19
     lamborghini
    1.18
     wien
    1.17
     eiffel
    1.17
     increa
    1.17
     stockholm
    1.16
     toledo
    1.15
    Activations Density 0.276%

    No Known Activations