© 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. 3696
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases and comparisons

    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
    382
    +0.10
    0.3%
    674
    +0.09
    0.3%
    468
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1243
    +0.10
    0.07
    1245
    +0.09
    0.06
    468
    +0.09
    0.05
    Negative Logits
     Châ
    -0.77
     déterminé
    -0.68
     Entra
    -0.67
     Palembang
    -0.67
     Doğ
    -0.66
     Söz
    -0.64
     avancé
    -0.62
     Bekasi
    -0.61
     Ağ
    -0.60
     Châte
    -0.60
    POSITIVE LOGITS
     snowing
    0.65
     imposible
    0.63
     easier
    0.61
     possible
    0.61
     impossible
    0.61
     raining
    0.60
     posible
    0.57
     difficult
    0.56
    商品説明
    0.56
    impossible
    0.56
    Activations Density 0.471%

    No Known Activations