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. 7-GEMMASCOPE-RES-16K
    6. 7092
    Prev
    Next
    INDEX
    Explanations

    method definitions and implementations related to string representation and hashing in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.89
    expandindo
    -0.89
    ///</
    -0.87
    twimg
    -0.84
     Normdatei
    -0.80
    URLException
    -0.79
    addPreferredGap
    -0.79
    ########.
    -0.78
     Administrativna
    -0.76
    AndEndTag
    -0.76
    POSITIVE LOGITS
     toString
    2.04
     ToString
    1.34
     hashCode
    1.09
    toString
    0.92
    ToString
    0.70
    repr
    0.65
    hashCode
    0.59
    جموع
    0.57
    OptionsMenu
    0.57
    toISOString
    0.56
    Activations Density 0.033%

    No Known Activations