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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 6596
    Prev
    Next
    INDEX
    Explanations

    instances of the text "cc" which may relate to content classification or identifier codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     điển
    -0.67
    gonic
    -0.66
    SequentialGroup
    -0.66
    gong
    -0.59
    DockStyle
    -0.59
    uchtet
    -0.59
    jala
    -0.58
     propOrder
    -0.56
    Gambas
    -0.55
    daction
    -0.54
    POSITIVE LOGITS
    cc
    3.04
    CC
    2.94
     CC
    2.73
     cc
    2.73
    Cc
    1.88
     Cc
    1.80
    ccs
    1.52
    CCG
    1.28
    CCB
    1.17
    ccc
    1.17
    Activations Density 0.117%

    No Known Activations