© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6654
    Prev
    Next
    INDEX
    Explanations

    terms related to "direct" as it pertains to interactions or applications in various contexts

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

    "Direct" followed by a related word

    np_acts-logits-general · gemini-2.0-flash

    direct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.82
    JNIEnv
    -0.74
     createSlice
    -0.73
     MotionEvent
    -0.71
    AfterClass
    -0.70
    endpush
    -0.69
    verifyException
    -0.69
    unmodifiable
    -0.68
     AssemblyCompany
    -0.67
    })));
    -0.66
    POSITIVE LOGITS
    orship
    0.75
     access
    0.62
    čar
    0.61
     impact
    0.61
     contact
    0.60
    ness
    0.55
     link
    0.55
     attack
    0.54
     links
    0.54
    пря
    0.52
    Activations Density 0.098%

    No Known Activations