© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14168
    Prev
    Next
    INDEX
    Explanations

    references to UFO sightings and investigations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    198
    +0.12
    0.3%
    946
    +0.10
    0.3%
    1987
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    671
    +0.12
    0.02
    1987
    +0.10
    0.03
    946
    +0.10
    0.04
    Negative Logits
    @[+][
    -0.60
    MigrationBuilder
    -0.57
     intptr
    -0.56
    +#+
    -0.56
    WithIOException
    -0.55
     AssemblyCulture
    -0.52
     OMITBAD
    -0.51
    __":
    -0.50
    ніципалі
    -0.50
     pinak
    -0.49
    POSITIVE LOGITS
     apprehen
    1.22
     pamph
    1.10
     unspeak
    1.06
     disagre
    1.04
     reluct
    1.03
     intrigu
    1.02
     encomp
    1.01
     depic
    1.01
     indescri
    1.00
     intersper
    0.97
    Activations Density 0.700%

    No Known Activations