© 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. 3353
    Prev
    Next
    INDEX
    Explanations

    terms related to casual attire and atmosphere

    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
    1363
    +0.16
    0.5%
    1870
    +0.12
    0.4%
    1557
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.16
    0.03
    544
    +0.12
    0.02
    1557
    +0.12
    0.02
    Negative Logits
     pessi
    -0.61
     poichè
    -0.60
     ovunque
    -0.56
     ridu
    -0.55
     immen
    -0.54
     altrett
    -0.53
     risult
    -0.53
     affinch
    -0.53
     chiaramente
    -0.51
     Spes
    -0.51
    POSITIVE LOGITS
     casual
    1.18
    casual
    1.06
    Casual
    1.02
     Casual
    1.02
     casually
    0.90
     informal
    0.84
    Informal
    0.75
     Informal
    0.68
     causal
    0.62
     tubercle
    0.61
    Activations Density 0.107%

    No Known Activations