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. 14566
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'straight' and its derived forms

    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
    Portale
    -1.17
    #+#
    -1.08
    Demografia
    -0.93
    Notae
    -0.89
    RegistryLite
    -0.87
    icium
    -0.85
    PhysRevD
    -0.84
    apimachinery
    -0.83
    intios
    -0.83
    ModelSerializer
    -0.82
    POSITIVE LOGITS
     straight
    1.74
    straight
    1.65
     Straight
    1.63
    Straight
    1.62
     STRA
    1.34
    直
    1.02
     strait
    0.97
     straightforward
    0.96
     straightening
    0.88
     straighten
    0.88
    Activations Density 0.074%

    No Known Activations