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. 24-GEMMASCOPE-RES-16K
    6. 12838
    Prev
    Next
    INDEX
    Explanations

    keywords related to therapy and mental health support

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

    Numbers in brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers in parentheses and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.09
     nahilalakip
    -0.97
     AssemblyCulture
    -0.95
     <=",
    -0.92
    UnusedPrivate
    -0.91
     Theſe
    -0.87
    styleType
    -0.87
    queryInterface
    -0.86
     мәкал
    -0.85
     Efq
    -0.85
    POSITIVE LOGITS
    <unused63>
    0.52
    <unused61>
    0.49
    <unused62>
    0.47
    funeralhome
    0.45
    <unused60>
    0.45
     PICTOGRAM
    0.44
     jelent
    0.43
    racycline
    0.42
     policiales
    0.42
    fetchall
    0.41
    Activations Density 0.530%

    No Known Activations