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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5782
    Prev
    Next
    INDEX
    Explanations

    instances of the word "forgot" and its variations, indicating a focus on themes of memory and recollection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignore
    -0.53
     kasarigan
    -0.47
    Ignore
    -0.45
     Across
    -0.44
     Ignore
    -0.44
    Across
    -0.41
    obe
    -0.41
     ACROSS
    -0.40
     ignore
    -0.38
     ign
    -0.38
    POSITIVE LOGITS
     forgotten
    2.31
     forgot
    2.27
    forgotten
    1.96
     Forgotten
    1.82
    Forgotten
    1.80
     neglected
    1.72
     Forgot
    1.71
    forgot
    1.65
     overlooked
    1.58
     забы
    1.55
    Activations Density 0.081%

    No Known Activations