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. 12-GEMMASCOPE-RES-16K
    6. 15788
    Prev
    Next
    INDEX
    Explanations

    names of authors and contributors in a scholarly context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.80
     distanciation
    -0.79
    NameInMap
    -0.77
    CppMethod
    -0.74
    extAlignment
    -0.70
    protoimpl
    -0.67
     Ause
    -0.67
    WebVitals
    -0.65
    ScopeManager
    -0.65
     nakalista
    -0.64
    POSITIVE LOGITS
    jsonwebtoken
    0.46
    def
    0.43
    CodedInputStream
    0.42
    ঔ
    0.41
    ("/{
    0.40
     ($\
    0.40
    libft
    0.39
    fficacy
    0.38
    ^{(\
    0.37
    вои
    0.37
    Activations Density 0.240%

    No Known Activations