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. 18-GEMMASCOPE-RES-16K
    6. 3233
    Prev
    Next
    INDEX
    Explanations

    specific numerical or coded elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hyphens followed by hexadecimal strings

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    VolleyError
    -0.46
    lograph
    -0.44
    ++)
    
    -0.43
    itude
    -0.43
    Queryable
    -0.42
    antium
    -0.42
     szer
    -0.41
     hard
    -0.41
    <?>>
    -0.41
    iform
    -0.40
    POSITIVE LOGITS
    QMetaType
    0.80
    MetaType
    0.78
    ValueStyle
    0.77
     Infórmanos
    0.74
    GOTREF
    0.69
    IndentedString
    0.69
    tagHelperRunner
    0.68
    MLLoader
    0.63
    IntoConstraints
    0.63
     Lordships
    0.63
    Activations Density 0.210%

    No Known Activations