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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10120
    Prev
    Next
    INDEX
    Explanations

    code related to variable declarations and types in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     شم
    -0.53
     security
    -0.53
    raven
    -0.51
     Forest
    -0.46
    anter
    -0.45
     Security
    -0.44
     semp
    -0.43
    ingu
    -0.43
     flas
    -0.43
     forest
    -0.42
    POSITIVE LOGITS
     float
    1.18
    float
    1.16
     {:.
    0.99
     Float
    0.99
    Float
    0.98
     floats
    0.96
     FLOAT
    0.94
    ("%.
    0.92
    FloatField
    0.91
     floating
    0.84
    Activations Density 0.933%

    No Known Activations