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. 17-GEMMASCOPE-RES-16K
    6. 7343
    Prev
    Next
    INDEX
    Explanations

    emotional responses and reflections on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AntiForgeryToken
    -0.67
    ])));
    -0.65
     &___
    -0.64
    bitField
    -0.63
    migrationBuilder
    -0.63
     vectoriales
    -0.62
    ]--;
    -0.60
     quæ
    -0.60
    )"),
    -0.60
     nakalista
    -0.59
    POSITIVE LOGITS
     when
    0.61
    WriteTagHelper
    0.59
    antMatchers
    0.52
    nologue
    0.49
    WRAPPER
    0.48
     Rial
    0.47
     vis
    0.46
    triangleq
    0.46
    ết
    0.44
    umacher
    0.44
    Activations Density 0.293%

    No Known Activations