© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8857
    Prev
    Next
    INDEX
    Explanations

    future-oriented statements or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.76
     SEDS
    -0.55
     critical
    -0.55
    tonsoft
    -0.53
     Pristupljeno
    -0.52
    RTHOOK
    -0.51
     المعيارى
    -0.51
    critical
    -0.51
    мум
    -0.51
     号
    -0.49
    POSITIVE LOGITS
     miss
    0.58
    Xna
    0.56
     gladly
    0.55
     volon
    0.53
    multirow
    0.51
     reserving
    0.51
     need
    0.50
    soon
    0.49
    CDATA
    0.49
     misses
    0.48
    Activations Density 0.167%

    No Known Activations