© 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. 5-GEMMASCOPE-RES-16K
    6. 9633
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edback
    -0.51
    glClear
    -0.51
    ⊰
    -0.48
    inella
    -0.47
    didSet
    -0.46
     pages
    -0.46
    tears
    -0.46
     nô
    -0.45
     situations
    -0.45
     True
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.82
    Datuak
    0.79
    <bos>
    0.78
    Personendaten
    0.66
     indisponible
    0.66
    PMailer
    0.64
     الرياضيه
    0.63
     userSchema
    0.60
    awaiter
    0.60
    tagHelperRunner
    0.60
    Activations Density 0.375%

    No Known Activations